This is the code for "How to Simulate a Self-Driving Car" by Siraj Raval on Youtube
Python Jupyter Notebook
Switch branches/tags
Nothing to show
Clone or download
Latest commit 8805a0f May 28, 2017
llSourcell committed May 28, 2017 Merge pull request #6 from iamBedant/master
Dataframe Heading Bug Fix


This is the code for "How to Simulate a Self-Driving Car" by Siraj Raval on Youtube

This video will be released on Wednesday, May 17th at 10 AM PST. This code is a work in progress.


This is the code for this video on Youtube by Siraj Raval. We're going to use Udacity's self driving car simulator as a testbed for training an autonomous car.


You can install all dependencies by running one of the following commands

You need a anaconda or miniconda to use the environment setting.

# Use TensorFlow without GPU
conda env create -f environments.yml 

# Use TensorFlow with GPU
conda env create -f environment-gpu.yml

Or you can manually install the required libraries (see the contents of the environemnt*.yml files) using pip.


Run the pretrained model

Start up the Udacity self-driving simulator, choose a scene and press the Autonomous Mode button. Then, run the model as follows:

python model.h5

To train the model

You'll need the data folder which contains the training images.


This will generate a file model-<epoch>.h5 whenever the performance in the epoch is better than the previous best. For example, the first epoch will generate a file called model-000.h5.


The credits for this code go to naokishibuya. I've merely created a wrapper to get people started.